Welfare-Centric Clustering

Claire Jie Zhang, Seyed A. Esmaeili, Jamie Heather Morgenstern
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:1684-1692, 2026.

Abstract

Fair clustering has traditionally focused on ensuring equitable group representation or equalizing group-specific clustering costs. However, Dickerson et al. recently showed that these fairness notions may yield undesirable or unintuitive clustering outcomes and advocated for a welfare-centric clustering approach that models the utilities of the groups. In this work, we model group utilities based on both distances and proportional representation and formalize two optimization objectives based on welfare-centric clustering: the Rawlsian (Egalitarian) objective and the Utilitarian objective. We introduce novel algorithms for both objectives and prove theoretical guarantees for them. Empirical evaluations on multiple real-world datasets demonstrate that our methods significantly outperform existing fair clustering baselines.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-zhang26b, title = { Welfare-Centric Clustering }, author = {Zhang, Claire Jie and Esmaeili, Seyed A. and Morgenstern, Jamie Heather}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {1684--1692}, year = {2026}, editor = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya}, volume = {300}, series = {Proceedings of Machine Learning Research}, month = {02--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v300/main/assets/zhang26b/zhang26b.pdf}, url = {https://proceedings.mlr.press/v300/zhang26b.html}, abstract = { Fair clustering has traditionally focused on ensuring equitable group representation or equalizing group-specific clustering costs. However, Dickerson et al. recently showed that these fairness notions may yield undesirable or unintuitive clustering outcomes and advocated for a welfare-centric clustering approach that models the utilities of the groups. In this work, we model group utilities based on both distances and proportional representation and formalize two optimization objectives based on welfare-centric clustering: the Rawlsian (Egalitarian) objective and the Utilitarian objective. We introduce novel algorithms for both objectives and prove theoretical guarantees for them. Empirical evaluations on multiple real-world datasets demonstrate that our methods significantly outperform existing fair clustering baselines. } }
Endnote
%0 Conference Paper %T Welfare-Centric Clustering %A Claire Jie Zhang %A Seyed A. Esmaeili %A Jamie Heather Morgenstern %B Proceedings of The 29th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2026 %E Emtiyaz Khan %E Yingzhen Li %E Arno Solin %E Aaditya Ramdas %F pmlr-v300-zhang26b %I PMLR %P 1684--1692 %U https://proceedings.mlr.press/v300/zhang26b.html %V 300 %X Fair clustering has traditionally focused on ensuring equitable group representation or equalizing group-specific clustering costs. However, Dickerson et al. recently showed that these fairness notions may yield undesirable or unintuitive clustering outcomes and advocated for a welfare-centric clustering approach that models the utilities of the groups. In this work, we model group utilities based on both distances and proportional representation and formalize two optimization objectives based on welfare-centric clustering: the Rawlsian (Egalitarian) objective and the Utilitarian objective. We introduce novel algorithms for both objectives and prove theoretical guarantees for them. Empirical evaluations on multiple real-world datasets demonstrate that our methods significantly outperform existing fair clustering baselines.
APA
Zhang, C.J., Esmaeili, S.A. & Morgenstern, J.H.. (2026). Welfare-Centric Clustering . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:1684-1692 Available from https://proceedings.mlr.press/v300/zhang26b.html.

Related Material